23 112

Jeff Wadsworth

jeffwadsworth

jeffwadsworth

AI & ML interests

Machine Learning

Recent Activity

new activity 9 days ago

Qwen/QwQ-32B:When will you fix the model replies missing</think>\n start tags

new activity 9 days ago

Qwen/QwQ-32B:Doesn't Generate `<think>` tags

liked a Space about 1 month ago

Qwen/Qwen2.5-Max-Demo

View all activity

Organizations

None yet

jeffwadsworth's activity

New activity in Qwen/QwQ-32B 9 days ago

When will you fix the model replies missing</think>\n start tags

#19 opened 9 days ago by

xldistance

Doesn't Generate `<think>` tags

#25 opened 9 days ago by

bingw5

New activity in Qwen/QVQ-72B-Preview 3 months ago

[ERROR] safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer

#3 opened 3 months ago by

luckychao

New activity in deepseek-ai/DeepSeek-V3-Base 3 months ago

When using the web version of DeepSeek v3, it keeps repeating responses without stopping.

#12 opened 3 months ago by

Nydaym

New activity in mattshumer/Reflection-Llama-3.1-70B 6 months ago

Works very well, but I had an issue with the following prompt timing out.

#3 opened 6 months ago by

jeffwadsworth

9.9 vs 9.11 example

#19 opened 6 months ago by

IlyaGusev

New activity in microsoft/Phi-3-mini-128k-instruct 11 months ago

a few edits for your model card (sorry I'm a grammar/writing nerd)

#16 opened 11 months ago by

luke-data-leader

New activity in miqudev/miqu-1-70b about 1 year ago

Model

#5 opened about 1 year ago by

mrfakename

New activity in TheBloke/CodeLlama-70B-Python-GGUF about 1 year ago

How to combine split files?

#1 opened about 1 year ago by deleted

New activity in TheBloke/Mixtral-8x7B-v0.1-GGUF about 1 year ago

My cpu is only using 50% of its cores.

#15 opened about 1 year ago by

jeffwadsworth

New activity in SkunkworksAI/phi-2 over 1 year ago

model missing

#1 opened over 1 year ago by

barius

New activity in TheBloke/deepseek-llm-67b-chat-GGUF over 1 year ago

This is a very impressive model. Using the 8bit version.

#2 opened over 1 year ago by

jeffwadsworth

New activity in TheBloke/Starling-LM-7B-alpha-GGUF over 1 year ago

Tokenizer issue?

#1 opened over 1 year ago by

sleepyjoecheated

New activity in TheBloke/Llama-2-70B-Chat-GGML over 1 year ago

Unzip problem

#15 opened over 1 year ago by

ShubhangiV

New activity in TheBloke/WizardCoder-Python-34B-V1.0-GGUF over 1 year ago

This model looks insanely good for coding ( 73.2 for humanEval )!

#1 opened over 1 year ago by

mirek190

New activity in TheBloke/Airoboros-L2-70B-2.1-GGUF over 1 year ago

Are the weights updated?

#1 opened over 1 year ago by

krao

New activity in TheBloke/StableBeluga2-70B-GGML over 1 year ago

Performance of quantified models

#3 opened over 1 year ago by

danielus

New activity in TheBloke/GodziLLa2-70B-GGML over 1 year ago

Finally got around to testing this model.

#1 opened over 1 year ago by

jeffwadsworth

New activity in TheBloke/Wizard-Vicuna-7B-Uncensored-GGML almost 2 years ago

This model is amazing.

#1 opened almost 2 years ago by

jeffwadsworth

New activity in TheBloke/OpenAssistant-SFT-7-Llama-30B-GGML almost 2 years ago

Prompts

#2 opened almost 2 years ago by

spirilis